Presentation 1993/9/22
LSI Module Placement Methos Based on Vector Quantization by Kohonen Networks
Takeshi Inoue, Shigeo Abe, Masahiro Kayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a method for solving an LSI Module placement ploblem by the Kohonen networks.First we explain relationship between the feature map and the neiborhood functions in the Kohonen networks.Namely,the feature map places that each synapse weight vector at the gravitational center of the remaining synapse weight vectors. Then,we show how to set the neiborhood functions to solve the problem of discrete microstructure,which is a fatal defect in solving the placement problem using the Kohonen networks. Finally,by computer simulations we show that the performance of the Kohonen networks is between those of the simulated annealing and the Min-Cut methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kohonen network / Self organization / Feature map / Weibor hood tunctions / LSI module placement
Paper # NC93-40
Date of Issue

Conference Information
Committee NC
Conference Date 1993/9/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) LSI Module Placement Methos Based on Vector Quantization by Kohonen Networks
Sub Title (in English)
Keyword(1) Kohonen network
Keyword(2) Self organization
Keyword(3) Feature map
Keyword(4) Weibor hood tunctions
Keyword(5) LSI module placement
1st Author's Name Takeshi Inoue
1st Author's Affiliation Hitach Research Laboratory Hitach Ltd.()
2nd Author's Name Shigeo Abe
2nd Author's Affiliation Hitach Research Laboratory Hitach Ltd.
3rd Author's Name Masahiro Kayama
3rd Author's Affiliation Hitach Research Laboratory Hitach Ltd.
Date 1993/9/22
Paper # NC93-40
Volume (vol) vol.93
Number (no) 247
Page pp.pp.-
#Pages 9
Date of Issue